자료유형 | 학위논문 |
---|---|
서명/저자사항 | Fluorescence, Scattering and Refraction in Computer Vision, with a Taste of Deep Learning. |
개인저자 | Murez, Zachary. |
단체저자명 | University of California, San Diego. Computer Science. |
발행사항 | [S.l.]: University of California, San Diego., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 119 p. |
기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
ISBN | 9780438169463 |
학위논문주기 | Thesis (Ph.D.)--University of California, San Diego, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Advisers: David Kriegman |
요약 | Physics based vision attempts to model and invert light transport in order to extract information (such as 3D shape and reflectance properties) about a scene from one or more images. In order for the inversion of the model to be tractable, many |
요약 | On the other-hand, learning based vision ignores the underlying physics and instead models observations of the world statistically. A prime example of this is deep learning, which has recently revolutionized computer vision tasks such as classif |
요약 | These two approaches to vision have traditionally been relatively disjoint, but are beginning to see some overlap. This thesis extends the state-of-the-art on both sides as well as brings them closer together. |
요약 | First the novel use of imaging fluorescence for 3D reconstruction from shape from shading and photometric stereo is proposed. This is achieved by leveraging the previously unexploited fact that fluorescence emission is isotropic making it an ide |
요약 | Second, photometric stereo is extended to work in participating media by accounting for how scattering affects image formation. The first insight is that in this situation fluorescence can be used to optically remove backscatter which significan |
요약 | Next the problem of single image dynamic refractive distortion correction is tackled. Previous work has attacked this problem using physics based approaches and as such requires additional information, such as high frame rate video or templates, |
요약 | Finally, the failure to train the model using synthetic data prompted the investigation of domain adaptation. A novel framework for unsupervised domain adaptation building off the ideas of adversarial discriminative feature matching and image-to |
일반주제명 | Computer science. |
언어 | 영어 |
바로가기 | ![]() |